© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70242
    Prev
    Next
    INDEX
    Explanations

    need for or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    王爷
    -1.82
     fré
    -1.74
    鬻
    -1.72
    鬭
    -1.69
     navide
    -1.66
    刳
    -1.65
     oiseau
    -1.61
     Antibodies
    -1.59
    糹
    -1.57
     compagnon
    -1.55
    POSITIVE LOGITS
    It
    1.78
    慤
    1.66
    。“
    1.66
     عندما
    1.65
    You
    1.63
    ().
    1.59
    に
    1.59
     be
    1.59
    ।
    1.53
    There
    1.52
    Activations Density 0.009%

    No Known Activations